Signal processing of landing radar considering irradiated surface characteristics using convolutional neural networks

In this paper, a signal-processing method for a lunar lander using deep learning is proposed. The ability for pinpoint soft landing on a lunar/planetary surface broadens the range of scientific and exploration missions. To perform pinpoint landing, measurement of the relative velocity with respect to the surface is essential. Landing radar is a sensor that measures the relative velocity. To measure the velocity, the landing radar irradiates the surface with a pulse wave and observes the Doppler shift. High-precision measurement on complex terrains, a crater, or a slope has always been the problem of landing radar because the irradiated terrains strongly affect the accuracy. We propose a measurement system that performs with high accuracy on complex terrains using convolutional neural networks. Moreover, we confirm that the proposed method could improve the measurement accuracy compared with the existing method.